|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pp-mod-subj2-lstm-0 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# pp-mod-subj2-lstm-0 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.0215 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 0 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 3052726 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7865 | 0.03 | 76320 | 4.7973 | |
|
| 4.502 | 1.03 | 152640 | 4.5167 | |
|
| 4.3567 | 0.03 | 228960 | 4.3828 | |
|
| 4.272 | 1.03 | 305280 | 4.3003 | |
|
| 4.2106 | 2.03 | 381600 | 4.2449 | |
|
| 4.1566 | 0.03 | 457920 | 4.2046 | |
|
| 4.118 | 1.03 | 534240 | 4.1734 | |
|
| 4.0851 | 0.03 | 610560 | 4.1498 | |
|
| 4.0563 | 1.03 | 686880 | 4.1309 | |
|
| 4.0367 | 0.03 | 763200 | 4.1159 | |
|
| 4.0134 | 1.03 | 839520 | 4.1037 | |
|
| 3.9977 | 2.03 | 915840 | 4.0930 | |
|
| 3.9827 | 0.03 | 992160 | 4.0838 | |
|
| 3.9706 | 1.03 | 1068480 | 4.0765 | |
|
| 3.9551 | 2.03 | 1144800 | 4.0699 | |
|
| 3.9406 | 0.03 | 1221120 | 4.0643 | |
|
| 3.9305 | 1.03 | 1297440 | 4.0594 | |
|
| 3.9228 | 2.03 | 1373760 | 4.0555 | |
|
| 3.9128 | 0.03 | 1450080 | 4.0514 | |
|
| 3.9095 | 1.03 | 1526400 | 4.0483 | |
|
| 3.9058 | 2.03 | 1602720 | 4.0453 | |
|
| 3.8955 | 0.03 | 1679040 | 4.0415 | |
|
| 3.8886 | 1.03 | 1755360 | 4.0394 | |
|
| 3.8803 | 2.03 | 1831680 | 4.0366 | |
|
| 3.8745 | 0.03 | 1908000 | 4.0354 | |
|
| 3.8719 | 1.03 | 1984320 | 4.0332 | |
|
| 3.8664 | 0.03 | 2060640 | 4.0317 | |
|
| 3.8623 | 1.03 | 2136960 | 4.0308 | |
|
| 3.8597 | 0.03 | 2213280 | 4.0296 | |
|
| 3.8551 | 1.03 | 2289600 | 4.0285 | |
|
| 3.8488 | 0.03 | 2365920 | 4.0273 | |
|
| 3.8429 | 0.03 | 2442240 | 4.0266 | |
|
| 3.8403 | 0.03 | 2518560 | 4.0258 | |
|
| 3.8406 | 1.03 | 2594880 | 4.0251 | |
|
| 3.8341 | 0.03 | 2671200 | 4.0244 | |
|
| 3.8346 | 1.03 | 2747520 | 4.0237 | |
|
| 3.8395 | 0.03 | 2823840 | 4.0231 | |
|
| 3.8338 | 0.03 | 2900160 | 4.0225 | |
|
| 3.8315 | 1.03 | 2976480 | 4.0220 | |
|
| 3.8293 | 0.02 | 3052726 | 4.0215 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|